© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125047
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebellion
    -0.07
    iegel
    -0.06
    зн
    -0.06
    ëħĦëıĦ
    -0.06
     rebellion
    -0.06
    ÅĻen
    -0.06
    маÑĢ
    -0.06
    monkey
    -0.05
     cos
    -0.05
     mess
    -0.05
    POSITIVE LOGITS
    ataire
    0.07
    orig
    0.07
     ÐĴики
    0.06
    own
    0.06
    uling
    0.06
    Literal
    0.06
    #ae
    0.06
    ám
    0.06
    eyed
    0.06
    parator
    0.06
    Activations Density 0.025%

    No Known Activations